Credential disclosure via LLM-controlled proxy routing
Published Jul 31, 2026 · Updated Jul 31, 2026
Incorrect authorization in Strands Agents Tools before 0.8.2 allows remote attackers to obtain configured credentials via prompt injection. The http_request tool lets the LLM set a proxies parameter after the request URL passes HTTP_REQUEST_TOKEN_CONFIG hostname checks, then adds the credential and sends the first hop through that proxy. Exploitation requires an agent that processes attacker-influenced content with HTTP_REQUEST_TOKEN_CONFIG configured; the result is cleartext Authorization-header disclosure without integrity or availability impact.
Summary
What happened
Incorrect authorization in Strands Agents Tools before 0.8.2 allows remote attackers to obtain configured credentials via prompt injection. The http_request tool lets the LLM set a proxies parameter after the request URL passes HTTP_REQUEST_TOKEN_CONFIG hostname checks, then adds the credential and sends the first hop through that proxy. Exploitation requires an agent that processes attacker-influenced content with HTTP_REQUEST_TOKEN_CONFIG configured; the result is cleartext Authorization-header disclosure without integrity or availability impact.
The record
- CVE
- CVE-2026-18394
- Published
- Jul 31, 2026
- Updated
- Jul 31, 2026
- Vendor
- Amazon Web Services
- Product
- Strands Agents Tools
- Classifications
- CWE-863, T1557
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 31, 2026CVE publishedPublication date reported by the CVE source.
- Jul 31, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <0.8.2
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo